© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2634
    Prev
    Next
    INDEX
    Explanations

    horsemanship-related words and phrases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    680
    +0.10
    0.3%
    506
    +0.10
    0.3%
    757
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.10
    0.04
    1343
    +0.10
    0.03
    1056
    +0.07
    0.03
    Negative Logits
    
    -0.74
    ⓧ
    -0.72
    <?
    -0.69
    /***
    -0.68
    </>
    -0.60
    /**
    -0.58
    PerformLayout
    -0.57
    hamshire
    -0.57
    <?
    -0.55
     cede
    -0.54
    POSITIVE LOGITS
     Hor
    0.99
     Simult
    0.88
     délib
    0.86
     LCD
    0.81
     Lafayette
    0.81
    LCD
    0.79
    Hor
    0.77
     véhic
    0.76
     Bartholo
    0.75
     Jä
    0.74
    Activations Density 0.219%

    No Known Activations